Speech Kit

by Alexander Brittain
5
4
3
2
1
Score: 59/100

Description

Speech and language toolkit for Obsidian

Reviews

No reviews yet.

Stats

32
stars
7,571
downloads
6
forks
92
days
2
days
2
days
466
total PRs
3
open PRs
50
closed PRs
413
merged PRs
111
total issues
2
open issues
109
closed issues
1,084
commits

Latest Version

2 days ago

Changelog

Highlights

  • Dictate while another app has focus. Turn on Desktop integration under Settings → Speech Kit → Capture to use a global shortcut or a menu bar or tray control. Keep Obsidian running with the destination note open. On macOS, the popover shows the target note and capture state.
  • More local transcription models. Try Qwen3 ASR 0.6B or 1.7B for multilingual file transcription and batch dictation, or Whisper Small Multilingual for a compact Whisper option. In dictation, Qwen3 ASR returns text after each phrase. The 1.7B model is a 2.52 GB download.

Improvements

  • Choose what stays visible. Put the dictation button in the ribbon, status bar, or both, or keep just commands and hotkeys. Use Advanced → Customize tools to hide translation, read-aloud, or AI tools and bring them back with their settings intact.
  • Clearer recording and transcript settings. Phrase timing and preset choices are easier to read. Timestamp settings show examples, and speaker settings help you switch to a compatible batch model. Speaker labels are estimates you can review after transcription.

Fixes

  • Keep track of text when something goes wrong. Dictation warns if the editor refuses a write and releases the microphone if the local engine exits. File transcription keeps recoverable text when it can't insert it, and longer files are processed within the model's per-phrase limits.
  • Use the tools together. Import available YouTube captions while dictating, browse for audio from a popout, cancel translation while it runs, and change read-aloud speed without resuming paused playback.

Compatibility

  • Updated local engine. When Speech Kit prompts you after updating, reinstall the local engine to get the new models and desktop controls. The model and hardware matrix lists the CPU, Metal, and CUDA options.

Known Limitations

  • Linux desktop controls depend on your session. The global shortcut needs a supported desktop portal, and the tray icon needs a compatible tray host. See the desktop controls guide.

README file from

Github

Dictate live. Transcribe audio and video files. Bring YouTube captions into your notes. Translate text. Listen to notes. One plugin inside the editor where your notes already live.

Local Dictation is now Speech Kit. It is the same plugin with the same local-first foundation, now with a name that fits what it has become. Existing installs, settings, and hotkeys carry over automatically.

Install Speech Kit from Obsidian Community Plugins

What it does

  • Dictate: Capture long sessions with live text and a choice of speech models.
  • Transcribe files: Drop in audio or video and turn its audio into a local transcript.
  • Import YouTube captions: Paste a link and bring available captions into your note without downloading the video.
  • Translate and listen: Translate notes locally and hear them read aloud with natural voices.
  • Refine with AI: Run a custom preset on a complete transcript or note using a local model or your chosen provider.

Choose the models that fit your workflow

Install the models you need in Settings → Speech Kit → Manage models. Available languages and performance depend on the model and your computer.

You want Models to consider
English live dictation Moonshine, English Nemotron, or Parakeet Unified
Multilingual live dictation Nemotron 3.5 ASR
File transcription or batch dictation Whisper, Cohere Transcribe, or Qwen3 ASR
Local voices Pocket TTS or Supertonic 3
Local translation Firefox Translations or Tencent HY-MT 2

The setup wizard helps you install the native engine and your first speech model. Review each model’s download size and license before installing it. NVIDIA streaming models run on CPU; performance and delay depend on your computer.

Dictate, transcribe, translate, listen, and refine

Dictate. Streaming words appear and revise in place while you speak. Finished text lands as Markdown at your cursor. Batch models show results after speech is processed.

Optional desktop dictation controls let you start and stop from a global shortcut or native status menu while another app has focus. Obsidian remains the destination and must stay running.

To keep microphone audio, enable Save microphone recording in Speech Kit settings. It is off by default and does not include system audio. When you stop dictation, Speech Kit saves the recording in Obsidian’s attachment location and adds an audio player to the note. Cancelling dictation discards the unfinished recording. Speech Kit also saves the audio if the sidecar stops the session because of an error or backlog. If the player cannot be added, Speech Kit keeps the recording and shows its link. If the recording itself cannot be completed, Speech Kit removes the incomplete file and shows a warning.

Transcribe files. Run Transcribe local audio file to turn an audio or video recording into text in the current note. Speech Kit extracts the audio with its media decoder and transcribes it with an installed batch speech model. Choose a language, model, timestamps, speaker labels, and paragraph style for that job. Your media stays on your computer.

Import YouTube captions. Run Transcribe YouTube video, paste a video link, and add its available captions to the current note. Choose the caption language and optional linked timestamps. This command needs an internet connection, but no speech model or video download. Videos without usable captions leave the note unchanged.

Both commands can optionally run one of your AI presets on the complete transcript. AI is separate from transcription; if you choose a remote provider, transcript text is sent to that provider. See the media transcription guide for setup and options.

Translate. Translate a selection or a whole note. Firefox Translations supports 96 English-anchored directions. Tencent HY-MT 2 supports direct translation among its 38 catalog languages. Preview the result before replacing your text, inserting it into the note, or copying it.

Listen. Read any note aloud with natural local voices. Control the voice, speed, and playback without leaving Obsidian.

Refine. Optional LLM tools can clean up, summarize, restructure, or transform text with your own prompts.

One toolkit across platforms

Speech Kit supports desktop Obsidian on macOS, Windows, and Linux. Acceleration and system-audio support depend on the platform and model.

Platform Architecture Acceleration System audio
macOS Apple silicon Model-dependent Metal macOS 14.2 or later
Windows x86-64, ARM64 (Snapdragon 8cx or newer) Optional NVIDIA CUDA (x86-64 only) Supported
Linux x86-64, ARM64 glibc (ARMv8.2 or newer, e.g. Raspberry Pi 5) Optional NVIDIA CUDA (x86-64 only) PulseAudio or PipeWire

For Linux and CUDA requirements, see the Linux guide and CUDA guide. Mobile Obsidian is not supported.

Models and acceleration

These are the execution paths in the current source and sidecar build configuration. A released install exposes the models included in its installed sidecar; recent additions may await a release.

Feature and model family macOS Apple silicon Windows x86-64 Windows ARM64 Linux x86-64 Linux ARM64
Batch speech · Whisper CPU / Metal CPU / CUDA* CPU CPU / CUDA* CPU
Batch speech · Qwen3 ASR CPU / Metal CPU / CUDA* CPU CPU / CUDA* CPU
Live dictation · Moonshine (English) CPU CPU CPU CPU CPU
Live dictation · Nemotron / Parakeet Unified CPU CPU CPU CPU CPU
Batch speech · Cohere Transcribe (English) CPU CPU CPU CPU CPU
Read aloud · Pocket TTS / Supertonic 3 CPU CPU CPU CPU CPU
Translation · Firefox Translations CPU CPU CPU CPU CPU
Translation · Tencent HY-MT 2 CPU / Metal CPU / CUDA* CPU CPU / CUDA* CPU

* CUDA requires the optional NVIDIA sidecar on Windows or Linux x86-64. Installing it does not accelerate the CPU-only families. Metal/CUDA entries identify available backend paths, not certification of every model on every GPU.

Qwen3 ASR offers managed 0.6B and 1.7B choices using the same batch/backend paths. Model language coverage varies. See model and hardware support for package boundaries, other GPUs, and validation coverage.

Getting started

  1. Install Speech Kit from Community Plugins.
  2. Follow the setup wizard to install the native engine and a speech model.
  3. Select Try dictation now, or use the ribbon, command palette, or a hotkey. To choose a status-bar control, open Settings → Speech Kit → Advanced → Customize tools.

Dictation, local file transcription, translation, and read aloud require no account, API key, usage credits, or cloud service. Once their models are installed, they continue working offline. YouTube caption import requires a connection to YouTube.

Optional AI text tools are separate. In Settings → Speech Kit, enable LLM features, then choose a provider and model under Provider and model. Use the sidebar for daily transform controls. See provider setup.

Language support

Each feature is served by a different model, so coverage is tracked per feature rather than as a single list.

Language Transcription Live dictation Read aloud Translation Interface
English, Spanish, German, French, Portuguese, Italian, Dutch, Japanese ✅ ✅ ✅ ✅ ✅
Croatian ✅ ✅ ✅ — ✅
Serbian ✅ — — — —

✅ supported · — not yet available

Coverage depends on the selected model: Whisper Large V3 Turbo covers the transcription languages above, while English models support English only. Multilingual live models do not currently cover Serbian. Translation coverage depends on the selected model. Firefox Translations covers English-anchored directions; Tencent HY-MT 2 supports all-to-all translation among 38 languages, including languages outside the table above.

Local-first, private by default

Speech Kit works without accounts, subscriptions, or required cloud services.

  • Your media stays on your machine. Dictation, local file transcription, read aloud, and translation run locally and continue working offline once their models are installed. YouTube caption import retrieves text from YouTube without downloading the video.
  • Local features need no account or API key. Optional remote providers may require an account, API key, or usage fees.
  • LLM tools are optional. Add flexible language processing to your workflow using a local model or a remote provider you choose. Text leaves your device only when you explicitly use a remote provider, and audio is never uploaded.
  • Choose what works for you. Install high-quality models suited to your language, hardware, and workflow.
  • Transparent and open. Downloads are explicit, third-party licenses are documented, and Speech Kit is open source.

Support development

If Speech Kit is useful to you, please support development:

Speech Kit pairs a TypeScript plugin with a Rust native sidecar. See CONTRIBUTING.md for its architecture, setup, and development workflow.

Community Plugin · Latest release

Issues · License

Third-party component and model licenses are documented in THIRD_PARTY_NOTICES.md. Model details link to each license; some models require you to review terms before installation.